8/1/24, 12:40 PM TEIT-10(1) - Jupyter Notebook

In [6]: import numpy as np;

import pandas as pd;
import dask.dataframe as dd;
import seaborn as sns;
import matplotlib.pyplot as mtp;

In [7]: df = pd.read_csv("Admission_Predict.csv")

In [8]: df

Out[8]: Serial GRE TOEFL University Chance of

Rating SOP LOR CGPA Research
No. Score Score Admit
1
1 337 118 0.92
0 4 4.5 4.5 9.65
1
2 324 107 0.76
1 4 4.0 4.5 8.87
1
3 316 104 0.72
2 3 3.0 3.5 8.00
1
4 322 110 0.80
3 3 3.5 2.5 8.67
0
5 314 103 0.65
4 2 2.0 3.0 8.21
...
... ... ... ...
... ... ... ... ...
1
396 324 110 0.82
395 3 3.5 3.5 9.04
1
397 325 107 0.84
396 3 3.0 3.5 9.11
1
398 330 116 0.91
397 4 5.0 4.5 9.45
0
399 312 103 0.67
398 3 3.5 4.0 8.78
1
400 333 117 0.95
399 4 5.0 4.0 9.66

400 rows × 9 columns

In [10]: dfd = dd.read_csv("Admission_Predict.csv")

In [11]: dfd
Out[11]: Dask DataFrame Structure:
Serial GRE TOEFL University Chance
SOP LOR CGPA Research
No. Score Score Rating of Admit

npartitions=1

int64 int64 int64 int64 float64 float64 float64 int64 float64

... ... ... ... ... ... ... ... ...

Dask Name: read-csv, 1 graph layer

localhost:8888/notebooks/TEIT-10 (1).ipynb 1/5

8/1/24, 12:35 PM TEIT-10 (1) - Jupyter Notebook

In [12]: df.head()

Out[12]: Serial GRE TOEFL University Chance of

Rating SOP LOR CGPA Research
No. Score Score Admit
1
1 337 118 0.92
0 4 4.5 4.5 9.65
1
2 324 107 0.76
1 4 4.0 4.5 8.87
1
3 316 104 0.72
2 3 3.0 3.5 8.00
1
4 322 110 0.80
3 3 3.5 2.5 8.67
0
5 314 103 0.65
4 2 2.0 3.0 8.21

In [13]: df.isnull()

Out[13]: Serial GRE TOEFL University Chance of

SOP LOR CGPA Research
No. Score Score Rating Admit
False False False False False
0 False False False False
False False False False False
1 False False False False
False False False False False
2 False False False False
False False False False False
3 False False False False
False False False False False
4 False False False False
... ... ... ... ...
... ... ... ... ...
False False False False False
395 False False False False
False False False False False
396 False False False False
False False False False False
397 False False False False
False False False False False
398 False False False False
False False False False False
399 False False False False

400 rows × 9 columns

In [14]: df.isnull().sum()

Out[14]: Serial No. 0

GRE Score 0
TOEFL Score 0
University Rating 0
SOP 0
LOR 0
CGPA 0
Research 0
Chance of Admit 0
dtype: int64

localhost:8888/notebooks/TEIT-10 (1).ipynb 2/5

8/1/24, 12:35 PM TEIT-10 (1) - Jupyter Notebook

In [15]: df.sum() Serial

Out[15]: No. 80200.00

GRE Score 126723.00
TOEFL Score 42964.00
University Rating 1235.00
SOP 1360.00
LOR 1381.00
CGPA 3439.57
Research 219.00
Chance of Admit 289.74
dtype: float64

In [16]: df = df.drop('Serial No.',axis=1)

In [17]: df

Out[17]: GRE Score TOEFL Score University Rating SOP LOR CGPA Research Chance of Admit

0 337 118 4 4.5 4.5 9.65 1 0.92

1 324 107 4 4.0 4.5 8.87 1 0.76

2 316 104 3 3.0 3.5 8.00 1 0.72

3 322 110 3 3.5 2.5 8.67 1 0.80

4 314 103 2 2.0 3.0 8.21 0 0.65

... ... ... ... ... ... ... ... ...

395 324 110 3 3.5 3.5 9.04 1 0.82

396 325 107 3 3.0 3.5 9.11 1 0.84

397 330 116 4 5.0 4.5 9.45 1 0.91

398 312 103 3 3.5 4.0 8.78 0 0.67

399 333 117 4 5.0 4.0 9.66 1 0.95

400 rows × 8 columns

In [18]: df.shape()

---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
Cell In[18], line 1
----> 1 df.shape()

TypeError: 'tuple' object is not callable

In [19]: df.shape

Out[19]: (400, 8)

localhost:8888/notebooks/TEIT-10 (1).ipynb 3/5

8/1/24, 12:35 PM TEIT-10(1) - Jupyter Notebook

In [20]: df['Chance of Admit '] = [1 if each > 0.75 else 0 for each in df['Chance of Adm

In [21]: df.head()
Out[21]: GRE Score TOEFL Score University Rating SOP LOR CGPA Research Chance of Admit

0 337 118 4 4.5 4.5 9.65 1 1

1 324 107 4 4.0 4.5 8.87 1 1

2 316 104 3 3.0 3.5 8.00 1 0

3 322 110 3 3.5 2.5 8.67 1 1

4 314 103 2 2.0 3.0 8.21 0 0

In [22]: x = df[['GRE Score', 'TOEFL Score', 'University Rating', 'SOP', 'LOR ', 'CGPA',
'Research']] #input on the x-axix

y = df['Chance of Admit '] #output on the y-axis

In [23]: from sklearn.model_selection import train_test_split

In [24]: x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.25,random_s

In [25]: print(f"Size of splitted data")

print(f"x_train {x_train.shape}")
print(f"y_train {y_train.shape}")
print(f"x_test {x_test.shape}")
print(f"y_test {y_test.shape}")
Size of splitted data
x_train (300, 7)
y_train (300,)
x_test (100, 7)
y_test (100,)

In [26]: from sklearn.tree import DecisionTreeRegressor

In [27]: model_dt = DecisionTreeRegressor(random_state=1)

In [29]: model_dt.fit(x_train,y_train)

Out[29]: DecisionTreeRegressor(random_state=1)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust
the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with
nbviewer.org.

In [30]: y_pred_dt = model_dt.predict(x_test) #int

localhost:8888/notebooks/TEIT-10(1).ipynb 4/5
8/1/24, 12:35 PM TEIT-10(1) - Jupyter Notebook

In [31]: from sklearn.metrics import ConfusionMatrixDisplay, accuracy_score

from sklearn.metrics import classification_report

In [33]: ConfusionMatrixDisplay.from_predictions(y_test,y_pred_dt)
mtp.title('Decision Tree')
mtp.show()
print(f" Accuracy is {accuracy_score(y_test,y_pred_dt)}")
print(classification_report(y_test,y_pred_dt))

Accuracy is 0.86
precision recall f1-score support

0 0.86 0.89 0.88 56

1 0.86 0.82 0.84 44

accuracy 0.86 100

macro avg 0.86 0.86 0.86 100
weighted avg 0.86 0.86 0.86 100

In [ ]:

localhost:8888/notebooks/TEIT-10(1).ipynb 5/5